| Speaker predicting apparatus, speaker predicting method, and program product for predicting speaker -> Monitor Keywords |
|
|
  Speaker predicting apparatus, speaker predicting method, and program product for predicting speakerUSPTO Application #: 20070120966Title: Speaker predicting apparatus, speaker predicting method, and program product for predicting speaker Abstract: A speaker predicting apparatus includes a speech detector that detects a person who is delivering a speech out of a plurality of persons, a feature extracting portion that extracts a feature in an image from the image in which the person is captured, a learning portion that learns the feature in the image occurring before the speech is detected by the speech detector, from the feature in the image, and a predicting portion that predicts the speaker out of the plurality of the persons, from the feature in the image in which the person is captured, with the use of a result learned by the learning portion. (end of abstract) Agent: Oliff & Berridge, PLC - Alexandria, VA, US Inventor: Kazumasa Murai USPTO Applicaton #: 20070120966 - Class: 348014080 (USPTO) The Patent Description & Claims data below is from USPTO Patent Application 20070120966. Brief Patent Description - Full Patent Description - Patent Application Claims
CROSS-REFERENCE TO RELATED APPLICATION [0001] This application claims priority under 35 USC 119 from Japanese patent document, 2005-339201, the disclosure of which is incorporated by reference herein. BACKGROUND [0002] 1. Technical Field [0003] This invention generally relates to a speaker predicting apparatus and a speaker predicting method. [0004] 2. Related Art [0005] In recent years, with higher speed and higher capacity of the communications line, the importance of teleconferencing system has been increasingly focused on. In a teleconferencing system, a conference or meeting can be held by connecting multiple sites located remotely to send and receive image signals and sound signals. Teleconferencing systems are favorable from a financial standpoint, because conference participants do not have to move between the remote sites. Also, as compared to a simple voice communication, the teleconferencing systems serve many uses as a communication tool, because the amount of information that can be sent and received is greatly increased. [0006] Conventionally, in order to specify the speaker in one of the conference rooms and selectively send the images and sounds of the speaker, an operator is needed for selectively changing cameras and a camera direction to capture the images and selectively changing microphones to collect the sounds. In a similar manner, when there are multiple participants in another conference room, another operator is also needed for a similar operation in another conference room. [0007] Under the circumstances, there has been proposed a teleconferencing system, by which it is possible to identify the speaker on the basis of the information on the image being captured. In this technique, an image of a face of a participant is extracted and a movement of lips thereof is captured in the image of the face, so as to detect a pre-action before speaking. Accordingly, the participant who is going to speak is identified as a speaker. [0008] However, in the a fore-described technique, the pre-action before speaking is detected. It is difficult to detect the speech or remarks before the speaker actually starts speaking. SUMMARY [0009] The present invention has been made in view of the above circumstances and provides a speaker predicting apparatus and a speaker predicting method that can predict a speaker before the speaker actually starts speaking. [0010] According to an aspect of the invention, there is provided a speaker predicting apparatus including a speech detector that detects a person who is delivering a speech out of a plurality of persons; a feature extracting portion that extracts a feature in an image from the image in which the person is captured; a learning portion that learns the feature in the image occurring before the speech is detected by the speech detector, from the feature in the image; and a predicting portion that predicts the speaker out of the plurality of the persons, from the feature in the image in which the person is captured, with the use of a result learned by the learning portion. BRIEF DESCRIPTION OF THE DRAWINGS [0011] Embodiments of the present invention will be described in detail based on the following figures, wherein: [0012] FIG. 1 is a schematic view illustrating a teleconferencing system according to an exemplary embodiment of the present invention; [0013] FIG. 2 schematically shows a block diagram illustrating a configuration of a speaker predicting apparatus according to an exemplary embodiment of the invention; [0014] FIG. 3 is a schematic view illustrating a second method of processing the image that a controller transmits to the conference room; [0015] FIG. 4 is a flowchart of an operation example 1 of the speaker predicting apparatus according to an exemplary embodiment of the present invention; [0016] FIG. 5 is a flowchart of an operation example 2 of the speaker predicting apparatus according to an exemplary embodiment of the present invention; and [0017] FIG. 6 is a flowchart of an operation example 3 of the speaker predicting apparatus according to an exemplary embodiment of the present invention. DETAILED DESCRIPTION [0018] A description will now be given, with reference to the accompanying drawings, of embodiments of the present invention. FIG. 1 is a schematic view illustrating a teleconferencing system 1000 according to an aspect of the present invention. In the teleconferencing system 1000 shown in FIG. 1, a communication is established between two conference rooms 100 and 200 on a public network 300 such as the Internet. [0019] Here, more conference rooms where a conference is being held may be provided. However, a description hereafter will be given on the assumption that the teleconferencing is being held between two conference rooms, for simplification of description. Also, the network used to communicate between the two conference rooms may employ the public network 300 without change. An alternative system may be employed such that privacy of communications can be protected as needed by, for example, a virtual private network (VPN) realized on the public network 300. Continue reading... Full patent description for Speaker predicting apparatus, speaker predicting method, and program product for predicting speaker Brief Patent Description - Full Patent Description - Patent Application Claims Click on the above for other options relating to this Speaker predicting apparatus, speaker predicting method, and program product for predicting speaker patent application. ###  How KEYWORD MONITOR works... a FREE service from FreshPatents1. Sign up (takes 30 seconds). 2. Fill in the keywords to be monitored. 3. Each week you receive an email with patent applications related to your keywords. Start now! - Receive info on patent apps like Speaker predicting apparatus, speaker predicting method, and program product for predicting speaker or other areas of interest. ### Previous Patent Application: Mobile video teleconferencing authentication and management system and method Next Patent Application: Videophone system and method Industry Class: Television ### FreshPatents.com Support Thank you for viewing the Speaker predicting apparatus, speaker predicting method, and program product for predicting speaker patent info. IP-related news and info Results in 5.65143 seconds Other interesting Feshpatents.com categories: Accenture , Agouron Pharmaceuticals , Amgen , AT&T , Bausch & Lomb , Callaway Golf |
||
